A Sensitivity Analysis of the MSMARCO Passage Collection
This analysis addresses concerns about data reliability for researchers using MSMARCO, but it is incremental as it validates existing practices rather than introducing new methods.
The study investigated whether retrieval system rankings on the MSMARCO passage collection would change if more passages per topic were considered relevant, finding that while individual scores varied, the relative system ordering remained stable, supporting the collection's original methodology.
The recent MSMARCO passage retrieval collection has allowed researchers to develop highly tuned retrieval systems. One aspect of this data set that makes it distinctive compared to traditional corpora is that most of the topics only have a single answer passage marked relevant. Here we carry out a "what if" sensitivity study, asking whether a set of systems would still have the same relative performance if more passages per topic were deemed to be "relevant", exploring several mechanisms for identifying sets of passages to be so categorized. Our results show that, in general, while run scores can vary markedly if additional plausible passages are presumed to be relevant, the derived system ordering is relatively insensitive to additional relevance, providing support for the methodology that was used at the time the MSMARCO passage collection was created.